Automatically Mapped Transfer between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines

By Haitham Bou-Ammar, Decebal Constantin Mocanu, Matthew E. Taylor, Kurt Driessens, Karl Tuyls, Gerhard Weiss. 2013

26 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Matthew E. Taylor
2. Decebal Constantin Mocanu
3. Peter Stone
4. Karl Tuyls
5. Eric Eaton
6. Gerhard Weiss
7. Haitham Ammar
8. Kurt Driessens

In Statistical and Nonlinear Physics

1. Matthew E. Taylor
2. Phuong H. Nguyen
3. Eric Eaton
4. Peter Stone
5. Elena Mocanu
6. Antonio Liotta
7. Madeleine Gibescu
8. Karl Tuyls

Citations in the corpus

• Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data (2016, background): “Examples of these applications are: modeling human choice (Osogami and Otsuka, 2014), collaborative filtering (Salakhutdinov et al, 2007), information retrieval (Gehler et al, 2006), transfer learning (Ammar et al, 2013), or multi-class classification (Larochelle and Bengio, 2008).”
• An automated measure of MDP similarity for transfer in reinforcement learning (2014, background): “Recent work on autonomous transfer (Taylor, Jong, and Stone 2008; Ammar et al. 2012; 2013) has focused on the latter two items, leaving the automated selection of relevant source tasks (item a) as a largely unsolved problem, yet a critical one for successful transfer learning.”
• A topological insight into restricted Boltzmann machines (2016, background): “…research to large-scale industrial applications, due to its success in different real-world machine learning problems such as audio recognition (Lee et al, 2009), re-inforcement learning (Mnih et al, 2015), transfer learning (Ammar et al, 2013), and activity recognition (Mocanu et al, 2015).”